Quality control and filtering results from cellranger

Sample info and environment setup

PRJNA732205

setwd("/media/jacopo/Elements/re_align/MM/PRJNA732205/SAMN19314096/SRR14629348/")
# Load the libraries (from Sarah script + biomart)
library(tidyverse) # packages for data wrangling, visualization etc
library(Seurat) # scRNA-Seq analysis package
library(clustree) # plot of clustering tree 
library(ggsignif) # Enrich your 'ggplots' with group-wise comparisons
library(clusterProfiler) #The package implements methods to analyze and visualize functional profiles of gene and gene clusters.
library(org.Hs.eg.db) # Human annotation package neede for clusterProfiler
library(ggrepel) # extra geoms for ggplo2
library(patchwork) #multiplots
library(reticulate)

Load and process cellranger data

Load and do the QC for the cellranger data

#list.files(".")
dat <- Read10X(data.dir ="./out/counts_filtered/")
dat <- CreateSeuratObject(dat) # Create the seurat object from the 10x data
kb.initial <- dat@assays[["RNA"]]@counts@Dim[[2]]
cat("Initial number of cells:", kb.initial, 
    "\nNumber of genes:",  dat@assays[["RNA"]]@counts@Dim[[1]])
## Initial number of cells: 11074 
## Number of genes: 36601

Quality Control

Empty cells were already filtered, check for % mt RNA and death markers:

# first calculate the mitochondrial percentage for each cell
dat$percent_mt <- PercentageFeatureSet(dat, pattern="^MT.")
# make violin plots
mt_rna = 20
max_counts = 10000



# Check some feature-feature relationships
# % mt RNA vs n Counts, n Features vs n Counts
# Check some feature-feature relationships
# % mt RNA vs n Counts, n Features vs n Counts
VlnPlot(dat, features = c("nCount_RNA", "nFeature_RNA", "percent_mt"))  + geom_hline(yintercept=mt_rna, linetype = "dotted")

plot1 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "percent_mt")
plot1 <- plot1 + geom_hline(yintercept=mt_rna, linetype = "dotted")
plot2 <- FeatureScatter(dat, feature1 = "nCount_RNA", feature2 = "nFeature_RNA")
plot2 <- plot2 + geom_vline(xintercept = max_counts, linetype = "dotted")
plot1 

plot2

##  cells retained by mt RNA content ( 20 %): 7052 
##  percentage of retained cells: 63.68 %
## cells retained by counts ( 10000 ): 6749 
##  percentage of retained cells: 60.94 %

Check the distribution of the cells with low counts and control death markers:

min_counts = 200


hist(dat@meta.data$nCount_RNA, breaks = 100, xlab = "Counts")

hist(dat@meta.data$nCount_RNA, breaks = 100, xlab = "Counts", xlim = c(0,5000))

hist(dat@meta.data$nCount_RNA, breaks = 1000, xlab = "Counts", xlim = c(0,1000))
abline(v=min_counts, col="red", lty = 3)

The evident peak of cells with < 200 counts could contain dying cells.

# Subset the dataset to focus only on those cells with low counts
dat.lowcount <- subset(dat, subset = nCount_RNA < min_counts)

# Get the mean of the counts for each gene and sort them decreasing
meanCounts <- rowMeans(GetAssayData(object = dat.lowcount, slot = 'counts'))
meanCounts <- sort(meanCounts, decreasing = T)

# A boxplot can help to observe the distribution of the means
#boxplot(meanCounts)

# Print the most highly expressed genes
head(meanCounts, 30)
##      IGKC  IGHV3-11     IGHA1    MT-CO2       HBB    MALAT1     RPL39     RPL41 
## 7.4734411 6.1616628 4.8452656 3.1685912 2.9907621 1.9769053 1.5912240 1.1986143 
##    MT-ND3     RPL34     RPS27     RPLP1    EEF1A1      HBA2       B2M     RPS12 
## 1.1963048 1.1570439 1.0993072 1.0138568 0.9930716 0.9907621 0.8706697 0.8660508 
##    MT-CO1      CD74    MT-CYB     RPL10   MT-ND4L    RPS15A      RPS8     RPS28 
## 0.8429561 0.8383372 0.8360277 0.8244804 0.8083141 0.8060046 0.7829099 0.7829099 
##   MT-ATP6     RPL32     RPL13    MT-CO3     RPL30     RPL11 
## 0.7321016 0.7274827 0.6951501 0.6928406 0.6812933 0.6489607
## cells retained by counts ( 200 ): 6314 
##  percentage of retained cells: 57.02 %

dir.create("result")
saveRDS(dat, file = "./result/SAMN19314096_clean_QC.Rds")

Feature selection

#Normalize
dat <- NormalizeData(dat)
# Find the first 4000 variabe features
dat <- FindVariableFeatures(dat, selection.method = "vst", nfeatures = 4000)

Data scaling

Set mean expression to 0 and variance across 1 to avoid highly expressed genes drive the forwarding analyses. Since negative expression is meaningless, scaled data are useful only for UMAP and clustering

# scale data, the scaled data are saved in:
# dat[["RNA"]]@scale.data

all.genes <- rownames(dat)

dat <- ScaleData(dat, vars.to.regress = c("percent_mt","nCount_RNA"))

Dimensionality reduction

dat <- RunPCA(dat, features = VariableFeatures(object = dat), verbose = F, seed.use = 1)
print(dat[["pca"]], dims = 1:5, nfeatures = 5)
## PC_ 1 
## Positive:  ACTB, CRIP1, HMGN2, HMGB1, ACTG1 
## Negative:  IGKC, IGHV3-11, IGHA1, DERL3, IGHV3-48 
## PC_ 2 
## Positive:  FTL, SELENOK, IGKV1OR2-108, IGKV1-17, IGKV1D-39 
## Negative:  IGLL1, VPREB1, DNTT, STMN1, SOX4 
## PC_ 3 
## Positive:  TYROBP, FCER1G, ANXA1, LYZ, S100A8 
## Negative:  IGLL1, VPREB1, DNTT, STMN1, PCLAF 
## PC_ 4 
## Positive:  LYZ, S100A8, S100A9, FCN1, AIF1 
## Negative:  NKG7, GNLY, IL32, CST7, CCL5 
## PC_ 5 
## Positive:  IGKV1OR2-108, CST3, IGKV1D-39, PRDX4, CD9 
## Negative:  CCDC144A, PRPSAP2, XIST, NEAT1, FNDC3B

UMAP

UMAP is a graph-based method of clustering. The first step in this process is to construct a KNN graph based on the euclidean distance in PCA space:

dat <- FindNeighbors(dat, dims = 1:20)

The graph now can be used as input for the function runUMAP()

dat <- RunUMAP(dat, dims = 1:20, seed.use = 1)
DimPlot(dat, reduction = 'umap', seed = 1)

Final plots:

## QC metrics

## markers